5 citations · 12 across the 15 of their papers we have counts for
Showing 2020Show all
2 papers · 1 filter
cs.SE2020
Astraea: Grammar-based Fairness Testing
Ezekiel Soremekun, Sakshi Udeshi, Sudipta Chattopadhyay
Software often produces biased outputs. In particular, machine learning (ML) based software are known to produce erroneous predictions when processing discriminatory inputs. Such u…
cs.CV2020★ 2 cited
Towards Backdoor Attacks and Defense in Robust Machine Learning Models
Ezekiel Soremekun, Sakshi Udeshi, Sudipta Chattopadhyay
The introduction of robust optimisation has pushed the state-of-the-art in defending against adversarial attacks. Notably, the state-of-the-art projected gradient descent (PGD)-bas…